{"id":"W4384665361","doi":"10.1007/s00521-023-08696-6","title":"Comparing explanations in RL","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Downstream (manufacturing); Context (archaeology); Artificial intelligence; Reinforcement; Test (biology); Machine learning; Human–computer interaction; Data science; Psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000201537,0.00007404923,0.00009288473,0.0001846225,0.0002873064,0.0001323463,0.0003688674,0.0000248048,0.000001188215],"category_scores_gemma":[0.00002197263,0.00007946319,0.00001896612,0.001241015,0.0000322868,0.0001720897,0.0002263768,0.0001214446,0.0001178624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000179204,"about_ca_system_score_gemma":0.00001293906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007761217,"about_ca_topic_score_gemma":0.00006189291,"domain_scores_codex":[0.9991549,0.00003024,0.0001929311,0.0002874357,0.0001007234,0.000233797],"domain_scores_gemma":[0.9993989,0.0002103461,0.0000408408,0.0002584965,0.00003411288,0.00005723109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001345443,0.00007377043,0.02485839,0.00002484499,0.000005462145,0.00001225391,0.001999169,0.04746649,0.001673151,0.7409658,0.0009692249,0.1819501],"study_design_scores_gemma":[0.00005270543,0.000008897327,0.01918885,0.000009888284,9.94159e-7,0.000006613688,0.0001968973,0.9683172,0.0005196586,0.008853626,0.002740742,0.000104005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5782162,0.00006713911,0.4140835,0.002683142,0.0001020532,0.0003243251,0.000001107042,0.0007621415,0.003760413],"genre_scores_gemma":[0.9972105,0.00001061199,0.002463187,0.000132284,0.00005583031,0.00004459765,0.000005291126,0.000005009234,0.00007269214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9208506,"threshold_uncertainty_score":0.3240415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0647685377314945,"score_gpt":0.3219865554596638,"score_spread":0.2572180177281693,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}